An estimate on the reliability of prediction in the applications of electronic nose is essential, which has not been paid enough attention. An algorithm framework called conformal prediction is introduced in this work for discriminating different kinds of ginsengs with a home-made electronic nose instrument. Nonconformity measure based on k-nearest neighbors (KNN) is implemented separately as underlying algorithm of conformal prediction. In offline mode, the conformal predictor achieves a classification rate of 84.44% based on 1NN and 80.63% based on 3NN, which is better than that of simple KNN. In addition, it provides an estimate of reliability for each prediction. In online mode, the validity of predictions is guaranteed, which means that the error rate of region predictions never exceeds the significance level set by a user. The potential of this framework for detecting borderline examples and outliers in the application of E-nose is also investigated. The result shows that conformal prediction is a promising framework for the application of electronic nose to make predictions with reliability and validity.
Background Animal locomotion requires dynamic interactions between neural circuits, the body (typically muscles), and surrounding environments. While the neural circuitry of movement has been intensively studied, how these outputs are integrated with body mechanics (neuromechanics) is less clear, in part due to the lack of understanding of the biomechanical properties of animal bodies. Here, we propose an integrated neuromechanical model of movement based on physical measurements by taking Drosophila larvae as a model of soft-bodied animals. Results We first characterized the kinematics of forward crawling in Drosophila larvae at a segmental and whole-body level. We then characterized the biomechanical parameters of fly larvae, namely the contraction forces generated by neural activity, and passive elastic and viscosity of the larval body using a stress-relaxation test. We established a mathematical neuromechanical model based on the physical measurements described above, obtaining seven kinematic values characterizing crawling locomotion. By optimizing the parameters in the neural circuit, our neuromechanical model succeeded in quantitatively reproducing the kinematics of larval locomotion that were obtained experimentally. This model could reproduce the observation of optogenetic studies reported previously. The model predicted that peristaltic locomotion could be exhibited in a low-friction condition. Analysis of floating larvae provided results consistent with this prediction. Furthermore, the model predicted a significant contribution of intersegmental connections in the central nervous system, which contrasts with a previous study. This hypothesis allowed us to make a testable prediction for the variability in intersegmental connection in sister species of the genus Drosophila. Conclusions We generated a neurochemical model based on physical measurement to provide a new foundation to study locomotion in soft-bodied animals and soft robot engineering.
A method using electronic nose to discriminate 10 different species of dendrobium, which is a kind of precious herb with medicinal application, was developed with high efficiency and low cost. A framework named aggregated conformal prediction was applied to make predictions with accuracy and reliability for E-nose detection. This method achieved a classification accuracy close to 80% with an average improvement of 6.2% when compared with the results obtained by using traditional inductive conformal prediction. It also provided reliability assessment to show more comprehensive information for each prediction. Meanwhile, two main indicators of conformal predictor, validity and efficiency, were also compared and discussed in this work. The result shows that the approach integrating electronic nose with aggregated conformal prediction to classify the species of dendrobium with reliability and validity is promising.
Machine learning techniques are widely used for the diagnosis of cancers. In this study, we proposed a classification and prediction system for the diagnosis of gastric cancer based on saliva samples. Gastric cancer (GC) is classified into early gastric cancer (EGC) and advanced gastric cancer (AGC). The diagnosis of GC at an early stage will improve the survival rate. Computer-aided diagnostic (CAD) systems can assist the radiologists in the diagnosis of EGC. 220 saliva samples were collected from the non-cancerous and gastric cancerous persons and analyzed using high-performance liquid chromatography-mass spectrometry (HPLC-MS). Fourteen amino acid biomarkers were sufficient to distinguish the persons from malignant to benign and were observed in the saliva samples with dominant peaks. We used the support vector machine (SVM) for binary classification. The processed Raman dataset was used to train and test the developed model. SVM based neural networks were established using different kernels, which produced different results. Accuracy, specificity, sensitivity, and receiver operating characteristics (ROC) were used to evaluate the proposed classification model, along with mean average error (MAE), mean square Error (MSE), sum average error (SAE), and sum square error (SSE). We achieved an overall accuracy of 97.18%, specificity of 97.44%, and sensitivity of 96.88% for the proposed method. This established method owns the prospect of clinical translation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.